Research
The lab works on robust, identifiable and interpretable machine learning tools for scientific inference. We work on both core machine learning topics and the application of machine learning algorithms for scientific inference in the life sciences. Our research focus is on:
- Computational statistics for dynamical systems
- Representation learning, especially using contrastive learning and generative pre-training
- Hierarchical and compositional representation learning
- Identifiability and robustness of machine learning algorithms
- Applications to systems neuroscience and biology
The following is a list of key publications within these focus areas. For a full list of publications, see the research sections.
Sparse Autoencoders Reveal Selective Remapping of Visual Concepts During Adaptation
PatchSAE is a framework to extract interpretable concepts and their spatial attributions in vision transformers.
Self-supervised contrastive learning performs non-linear system identification
DynCL is a framework for non-linear system identification using contrastive learning.
Learnable Latent Embeddings for Joint Behavioral and Neural Analysis
CEBRA is a contrastive learning algorithm for relating behavior and neural activity.
Contrastive Learning Inverts the Data Generating Process
Contrastive learning with the InfoNCE objective can recover the ground truth latent factors underlying the data.
Improving Robustness against Common Corruptions by Covariate Shift Adaptation
Adapting batch norm statistics of trained computer vision models considerably increases robustness at test-time.
wav2vec: Unsupervised Pre-training for Speech Recognition
Contrastive pre-training on speech at scale reduces the need for labeled data.
